GLAS
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Medical Image Segmentation | GlaS | Dice96.91 | 106 | |
| Semantic Segmentation | GlaS | Dice90.62 | 59 | |
| Gland Segmentation | GlaS | mIoU0.8684 | 58 | |
| Medical Image Segmentation | GlaS (test) | Dice Score93.94 | 56 | |
| Binary Segmentation | GLAS | DSC92.35 | 28 | |
| Image Classification | GlaS | Accuracy98.75 | 26 | |
| Gland Segmentation | GlaS (test) | F1 Score91.49 | 22 | |
| Gland Segmentation | GlaS Challenge Dataset (test A) | F1 Score92 | 20 | |
| Medical Image Segmentation | GlaS 2017 (test) | Dice Coefficient89.97 | 19 | |
| Nuclei instance segmentation | GlaS (test) | Dice Coefficient72.1 | 19 | |
| Semantic Segmentation | GLaS (test) | mIoU76.06 | 13 | |
| Medical Image Segmentation | GlaS Histopathology (test) | IoU78.63 | 12 | |
| Localization | GlaS (test) | PxAP95.8 | 12 | |
| Classification | GlaS (test) | Accuracy100 | 11 | |
| Colorectal Histopathology Segmentation | GlaS MICCAI 2015 (test B) | Accuracy91.55 | 10 | |
| Colorectal Histopathology Segmentation | GlaS MICCAI 2015 (test A) | Accuracy92.96 | 10 | |
| Medical Image Segmentation | GlaS (three fixed-seed random data splits) | IoU88.72 | 8 | |
| Gland Segmentation | GlaS (5-fold cross val) | Dice85.2 | 8 | |
| 2D Image Segmentation | GlaS | Dice Score83.25 | 8 | |
| Image Classification | GlaS center-wise (test) | CL Score100 | 6 | |
| Object Localization | GlaS center-wise (test) | PxAP88.8 | 6 | |
| Segmentation | GlaS (internal held-out) | Dice Score89.3 | 5 | |
| Object Detection | GlaS (testB) | F1 Score73.45 | 5 | |
| Object Detection | GlaS (testA) | F-score0.9039 | 5 | |
| Nuclei Classification | GlaS transfer from Dpath (test) | Detection Score67.5 | 5 |
Showing 25 of 27 rows